Most powerful & flexible
usage stack for AI.
Control prices, limits, and contracts for users and agents, live.
The policy
One policy file:
credits, limits, contracts.
The policy runs inside your app and decides every call: what's allowed, what it's worth, and what it costs you.
allow() in your process. Node, Bun, Deno, the browser, Rust.policy:credits:ai_token: { price: { amount: 0.00002 }, overhead_cost: 0.000008 }plans:free:entitlements:chat: { limit: { credit: ai_token, value: 50000, resets: true } }pro:entitlements:chat: { limit: { credit: ai_token, mode: soft, value: 2000000, resets: true } }export_pdf: {} # no limit: a feature flag
const limitr = await Limitr.new(policy, 'yaml');await limitr.ensureCustomer('acme', 'pro');await limitr.allow('acme', 'export_pdf'); // trueawait limitr.allow('acme', 'chat', 2_100_000); // true, soft limit// event: meter-overage → bill acme: $2
The engine
Enforced inside your app.
Offline and sandboxed, durable for high-throughput AI. Open source and extensible, so it fits your business forever.
How the engine works →Control
Feature flags, hard and soft limits, spend caps, an agent's budget.
allow('ada', 'chat', 60_000) // falseBill
Usage pricing, credits, overage, one customer's contract. Margin known per call.
meter-overage → bill acme: $2Start with the engine alone. Limitr Cloud is a one-line change later, and never required.
Limitr Cloud
Controls and billing, live.
Hosted by us, edited by you. Change a plan, a price, or one customer's deal, test it on real traffic, then publish to every engine. No ticket, no release.
Change it live
Every engine has the change on its next call. Versioned, one click to revert.
Ledger to invoice
Usage lands in a ledger and rolls into invoices. Stripe built in, or your own rails.
Limitr Analyst
The agent in Cloud. Ask what a change will do, it simulates it on real usage, then writes it.
Agentic by design
Built for coding agents.
We think integration should be agentic. So Limitr is an open-source engine and usage stack that ships with skills: your agent learns the policy, the SDK, and the patterns, and does the work.
In Limitr Cloud, Limitr Analyst answers integration questions too, and can write the change for you.
Write the policy
Credits, plans, limits, prices, one customer's contract, from a plain brief. Tested before it ships.
Wire the SDK
allow() at the call, reserve and settle around the model, events to your billing, in your framework.
Build the surfaces
Usage views, plan pickers, billing settings, and internal controls in your own UI, read from the policy.
Answer the hard questions
Margin per customer, what a price change would do, where a cap should sit, from the engine's own events.